When I read an article, I am expecting to read the author's own experiences and insights they gained from them. Not the regurgitation of an industrial scale word generator.

> She still needed to know what questions to ask and prompts to give

Then publish the prompts. Let me enter them in an LLM of my choosing and see what bullshit it hallucinates and diff it against the 'article'.

> hopefully steered it right when it made up falsehoods.

"Hopefully"? Publishing something a stochastic parrot dreamed up under your name is ghost writing at best and spreading misinformation at worst.

The "insight" that I needed a map, and that I had effectively created a map from my research, reading and "prompting" was mine, but I have no problem with using fancy tooling to help me pull it all together.

If someone could've pointed me to some other fully laid out mapping of the CL tooling stack I would've been happy as the article was a rather time consuming side quest.

> something a stochastic parrot dreamed up

With more time and energy, human discovery and invention, the statistical mechanics backing the information digest will improve beyond any one human's lifetime internalization and idiosyncratic writings divined.

What I do see is somewhat curated cache of what stochastic parrot dreamed of so I don’t have to burn tokens myself.

As I understand author is interested in the topic and didn’t simply publish total hallucinations.